Zitnik Lab, HarvardHarvard Medical School lab; ToolUniverse 1.7k+ stars306 installs on skills.sh

Devtu Self Evolve

Orchestrate the full ToolUniverse self-improvement cycle: discover APIs.

Works in any agentClaude CodeCodexCursorClaude appChatGPT+ any other agent
mims-harvard/tooluniverse
Security state: reviewed

3 static scans, 0 counted findings.

Edge checks it again each time your agent loads it.

SKILL.md3 files · 32.5 KB

From the mims-harvard public repository. Edge did not write or edit this skill.

What it does

  • Orchestrate the full ToolUniverse self-improvement cycle: discover APIs, create tools, test with researcher personas, fix issues, optimize skills, and push via git.
  • References and dispatches to all other devtu skills.
  • Use when asked to: run the self-improvement loop, do a debug/test round, expand tool coverage, improve tool quality, or evolve ToolUniverse.
ZH

Why Zitnik Lab, Harvard

Biomedical informatics research lab at Harvard. Each fact links its public source.

  • Harvard affiliation

    The lab site links to Harvard Medical School's Department of Biomedical Informatics.

    Lab site
  • Nature Medicine paper

    The lab reports COMPASS, a cancer immunotherapy response model, published in Nature Medicine.

    Lab site
  • ToolUniverse repo

    The ToolUniverse repo has 1.7k+ GitHub stars.

    GitHub repo

Public sources, checked Oct 26, 2026.

How it works

  1. 1
    Copy

    Try for free gives you one prompt.

  2. 2
    Paste

    Paste it into Claude Code, Codex or Cursor.

  3. 3
    Ask

    Ask for the outcome. Your agent loads Devtu Self Evolve.

What you can inspect

3 static scans, 0 counted findings.

Security state at 2026-09-30: reviewed. Static scans check the code, not how well the skill works.

State definitions

Skill details

Security scansReviewed

3 static scans, 0 counted findings. Security state at 2026-09-30: reviewed. Edge checks it again each time your agent loads it.

Edge static checks (Edge-run): edge-static/1.0.1. Scope: Static patterns for remote execution, credentials with network sends, obfuscation, prompt overrides, hidden Unicode, binaries and persistence. Raw findings: .

Cisco skill-scanner (Edge-run): cisco-skill-scanner/2.1.0. Scope: Local static, YARA, pipeline and behavioral analyzers; no LLM or AI Defense analysis. Raw findings: 1.

Semgrep Edge rules (Edge-run): semgrep/1.178.0+edge-rules.c15016a36fd3+offline-v1. Scope: Six Edge-authored static rules with Semgrep CE; offline execution and metrics disabled. Semgrep-maintained rules excluded. Raw findings: .

Edge static checks
Pass · 0 counted findings · 2026-09-27
Cisco skill-scanner
Pass · 0 counted findings · 2026-09-27
Semgrep Edge rules
Pass · 0 counted findings · 2026-09-27
Creator, source & licencemims-harvard

From the mims-harvard public repository. Edge did not write or edit this skill.

Revision
40aabf8fbe7b153061f76eeb4be70415dc6f1126
Package hash
sha256:5a2dd4b34fe0b8c37743f8cdde056a45738dcc7a258cc5bb7dda08ea7a696cf9
Licence
Apache-2.0
Description
Orchestrate the full ToolUniverse self-improvement cycle: discover APIs, create tools, test with researcher personas, fix issues, optimize skills, and push via git. References and dispatches to all other devtu skills. Use when asked to: run the self-improvement loop, do a debug/test round, expand tool coverage, improve tool quality, or evolve ToolUniverse.
Quoted from the skill’s own description
Read skill files3 files

3 files, 32.5 KB at revision 40aabf8fbe7b.

Questions about Devtu Self Evolve

What does Devtu Self Evolve do?

Orchestrate the full ToolUniverse self-improvement cycle: discover APIs. Published by Zitnik Lab, Harvard (mims-harvard/tooluniverse).

Is Devtu Self Evolve safe to use?

Edge security state: Reviewed (3 Edge-run static scans, scanned Sep 30, 2026). The Evidence tab shows the scan.

How do I use Devtu Self Evolve in Claude Code, Codex or Cursor?

Click Try for free, pick your agent and follow its one step. Edge is free, with no Edge account.